QiCha's repositories
100knocks-preprocess
データサイエンス100本ノック（構造化データ加工編）
a_bccwj
Universal Dependencies online documentation
awesome-japanese-nlp-resources
A curated list of resources dedicated to Python libraries, pre-trained models, dictionaries, and corpora of NLP for Japanese
bert-book
「BERTによる自然言語処理入門: Transformersを使った実践プログラミング」サポートページ
bert-classification-tutorial
【2023年版】BERTによるテキスト分類
BERT_Japanese_Google_Colaboratory
Google Colaboratoryで日本語のBERTを動かす方法です。
bunkai
Sentence boundary disambiguation tool for Japanese texts (日本語文境界判定器)
buzz
linguistics backend
chatgpt-vscode
A VSCode extension that allows you to use ChatGPT inside the IDE
chiVe
Japanese word embedding with Sudachi and NWJC 🌿
d2l-zh
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被60个国家的400所大学用于教学。
data-science-ipython-notebooks
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
esupar
Tokenizer POS-Tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models for Japanese and other languages
ja_sentence_segmenter
japanese sentence segmentation library for python
jd-shopper
京东自动下单 (自动登录,指定时间预约商品,商品补货监控,自动加购物车,自动下单)
kwja
A unified language analyzer for Japanese
news-fetch
A Python Package which helps to scrape all news details from any news websites
newspaper
News, full-text, and article metadata extraction in Python 3. Advanced docs:
notebooks
Jupyter notebooks for the Natural Language Processing with Transformers book
numpy-100
100 numpy exercises (with solutions)
Python-100-Days
Python - 100天从新手到大师
sentence-transformers
Sentence Embeddings with BERT & XLNet
sentiment_ja
オリジナルのリポジトリがなくなったので、偶然直前にクローンしていたデータをアップロードしています。著作権、ライセンスはオリジナルに準じます。
SudachiTra
Japanese tokenizer for Transformers
SuPar-UniDic
Tokenizer POS-tagger Lemmatizer and Dependency-parser for modern and contemporary Japanese with BERT models
Transformers-Tutorials
This repository contains demos I made with the Transformers library by HuggingFace.
vaporetto
🛥 Vaporetto: a fast and lightweight pointwise prediction based tokenizer